On 01/06/15 09:50, Andriy Berestovskyy wrote:
> Hi Zoltan,
>
> On Fri, May 29, 2015 at 7:00 PM, Zoltan Kiss
> wrote:
>> The easy way is just to increase your buffer pool's size to make
>> sure that doesn't happen.
>
> Go for it!
I went for it, my question is whether is it a good and
Hi,
Anyone would like to review this patch? Venky sent a NAK, but I've
explained to him why it is a bug.
Regards,
Zoltan
On 27/05/15 21:12, Zoltan Kiss wrote:
> This check doesn't do what's required by rte_eth_tx_burst:
> "When the number of previously sent packets reached the "minimum
Hi Stephen,
On 5/29/2015 11:27 PM, Stephen Hemminger wrote:
> On Fri, 29 May 2015 16:45:25 +0800
> Cunming Liang wrote:
>
>> +#ifdef RTE_EAL_RX_INTR
>> +extern int
>> rte_eth_dev_rx_intr_ctl(uint8_t port_id, int epfd, int op, void *data);
>> +#else
>> +static inline int
>>
Remove these unnecessary vring descriptor length updating, vhost should not
change them.
virtio in front end should assign value to desc.len for both rx and tx.
Signed-off-by: Changchun Ouyang
---
lib/librte_vhost/vhost_rxtx.c | 18 +-
1 file changed, 1 insertion(+), 17
Extract codes into 2 common functions:
update_secure_len which is used to accumulate the buffer len in the vring
descriptors.
and fill_buf_vec which is used to fill struct buf_vec.
Signed-off-by: Changchun Ouyang
---
lib/librte_vhost/vhost_rxtx.c | 79
Remove unnecessary new line.
Signed-off-by: Changchun Ouyang
---
lib/librte_vhost/vhost_rxtx.c | 9 +++--
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c
index 5fe1b6c..de60e9b 100644
---
Vring enqueue need consider the 2 cases:
1. use separate descriptors to contain virtio header and actual data, e.g. the
first descriptor
is for virtio header, and then followed by descriptors for actual data.
2. virtio header and some data are put together in one descriptor, e.g. the
first
Fix enqueue/dequeue can't handle chained vring descriptors;
Remove unnecessary vring descriptor length updating;
Add support copying scattered mbuf to vring;
Changchun Ouyang (4):
lib_vhost: Fix enqueue/dequeue can't handle chained vring descriptors
lib_vhost: Refine code style
lib_vhost:
2015-05-12 05:30, Qiu, Michael:
> Hi, thomas
>
> What about this patch?
It seems this patch was not *really* sent to dev at dpdk.org.
Please re-send, keeping the Acked-by line.
> On 4/16/2015 4:09 PM, Chen, Jing D wrote:
> > From: Michael Qiu [mailto:qiudayu at cn.ibm.com]
> >> From: Michael
As unified packet types are used instead, those old bit masks and
the relevant macros for packet type indication need to be removed.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
examples/l3fwd/main.c |
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
Severl useless code lines are added accidently, which blocks packet
type unification. They should be deleted at all.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
Signed-off-by: Jijiang Liu
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
To unify packet type among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Note that around 2.5% performance drop (64B) was observed
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Signed-off-by: Helin Zhang
---
As there are only 6 bit flags in ol_flags for indicating packet
types, which is not enough to describe all the possible packet
types hardware can recognize. For example, i40e hardware can
recognize more than 150 packet types. Unified packet type is
composed of L2 type, L3 type, L4 type, tunnel
To unify the packet type, bit masks of packet type for ol_flags are
replaced. In addition, more packet types (UDP, TCP and SCTP) are
supported in vectorized ixgbe PMD.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_UNIFIED_PKT_TYPE, which is disabled by default.
Note
In order to unify the packet type, the field of 'packet_type' in
'struct rte_mbuf' needs to be extended from 16 to 32 bits.
Accordingly, some fields in 'struct rte_mbuf' are re-organized to
support this change for Vector PMD. As 'struct rte_kni_mbuf' for
KNI should be right mapped to 'struct
Hi Keunhong,
Thanks for your response. Seems ixgbe only supports hw timestamping for PTP
packets. But I still don?t understand why igb and e1000 support hw timestamping
all packets while ixgbe does not.
???: Keunhong Lee [mailto:dlrmsghd at gmail.com]
: 2015?6?1? 11:51
???: ?? ???
??:
when rte_atomic16_cmpset return 0 in first loop, secure_len
should be reset to 0 in second loop, otherwise (pkt_len > secure_len) always
be false, the num of desc maybe not enough
Signed-off-by: Wei li
---
lib/librte_vhost/vhost_rxtx.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
From: Ding Zhi
This variable has undefined values in some cases.
Fixes: 422a20a4e62d ("app/testpmd: fix uninitialized flow control variables")
Signed-off-by: Ding Zhi
Signed-off-by: David Marchand
---
app/test-pmd/cmdline.c |2 +-
1 file changed, 1 insertion(+), 1
From: Gaetan Rivet
Each test requires a certain minimal amount of memory.
Spreading memory on all sockets means that the test will get less memory than
what it wanted on multi sockets system.
So replace all_sockets() with per_sockets().
Also doubled memory on group_5 as
http://dpdk.org/browse/dpdk/tree/app/test-pmd/ieee1588fwd.c
This code example contains enabling PTP with intel NICs.
Keunhong.
2015-06-01 12:48 GMT+09:00 Keunhong Lee :
> 82599 supports hw timestamping for PTP packets.
> I don't know whether it supports timestamping for general packets.
>
>
82599 supports hw timestamping for PTP packets.
I don't know whether it supports timestamping for general packets.
http://lxr.free-electrons.com/source/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c#L640
says that
640
Acked-by: David Harton (dharton)
> -Original Message-
> From: Liang-Min Larry Wang [mailto:liang-min.wang at intel.com]
> Sent: Friday, May 29, 2015 8:38 PM
> To: dev at dpdk.org
> Cc: bruce.richardson at intel.com; konstantin.ananyev at intel.com; David
> Harton
> (dharton); Andrew
On 06/01/2015 11:30 AM, Jan Blunck wrote:
> In rte_log_dump_history() the log_history list is reinitialized without
> resetting the log_history_size. In the next call to rte_log_add_in_history()
> the log_history_size > RTE_LOG_HISTORY and the code unconditionally tries
> to remove the first
On Mon, Jun 1, 2015 at 10:31 AM, Olivier MATZ
wrote:
> Hi Jan,
>
> On 05/29/2015 12:34 PM, Jan Blunck wrote:
> > In rte_log_dump_history() the log_history list is reinitialized without
> > resetting the log_history_size. In the next call to
> rte_log_add_in_history()
> > the log_history_size >
As it's done in __rte_pktmbuf_prefree_seg(), we can avoid using an
atomic increment in rte_pktmbuf_attach() by checking if we are the
only owner of the mbuf first.
Signed-off-by: Olivier Matz
---
lib/librte_mbuf/rte_mbuf.h | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git
In rte_log_dump_history() the log_history list is reinitialized without
resetting the log_history_size. In the next call to rte_log_add_in_history()
the log_history_size > RTE_LOG_HISTORY and the code unconditionally tries
to remove the first entry:
Program received signal SIGSEGV, Segmentation
Do some cosmetic clean-up.
Signed-off-by: Olivier Matz
---
lib/librte_mempool/rte_dom0_mempool.c | 36
lib/librte_mempool/rte_mempool.c | 10 ++---
lib/librte_mempool/rte_mempool.h | 80 ++-
3 files changed, 73 insertions(+), 53
Each object stored in mempools are suffixed by a trailer, storing
a cookie in debug mode which help to detect memory corruptions.
Like for headers, introduce a structure that materializes the content of
this trailer.
Signed-off-by: Olivier Matz
---
lib/librte_mempool/rte_mempool.c | 4 +++-
Each object stored in mempools are prefixed by a header, allowing for
instance to retrieve the mempool pointer from the object. When debug is
enabled, a cookie is also added in this header that helps to detect
corruptions and double-frees.
Introduce a structure that materializes the content of
These 3 patches try to make mempool code easier to read, they
have no functional impact.
Olivier Matz (3):
mempool: introduce objhdr structure for object headers
mempool: introduce objtlr structure for object trailers
mempool: fix typos, indentation, and doxygen style
---
lib/librte_vhost/vhost_rxtx.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c
index 4809d32..fb3e72a 100644
--- a/lib/librte_vhost/vhost_rxtx.c
+++ b/lib/librte_vhost/vhost_rxtx.c
@@ -431,6 +431,7 @@ virtio_dev_merge_rx(struct
Hi Helin,
On 05/26/2015 10:36 AM, Helin Zhang wrote:
> Use the reserved 16 bits in rte_mbuf structure for the outer vlan,
> also add QinQ offloading flags for both RX and TX sides.
>
> Signed-off-by: Helin Zhang
> ---
> lib/librte_mbuf/rte_mbuf.h | 10 +-
> 1 file changed, 9
Hi Helin,
On 05/26/2015 10:36 AM, Helin Zhang wrote:
> Little endian to CPU order conversion had been added for reading
> vlan tag from RX descriptor, while its original source line was
> forgotten to delete. That's a discarded source line and should be
> deleted.
>
> Signed-off-by: Helin Zhang
Hi Zoltan,
On Fri, May 29, 2015 at 7:00 PM, Zoltan Kiss wrote:
> The easy way is just to increase your buffer pool's size to make
> sure that doesn't happen.
Go for it!
> But there is no bulletproof way to calculate such
> a number
Yeah, there are many places for mbufs to stay :( I would
Hi
I noticed that there is a patch which can set hardware timestamp for the
received
packets(http://www.wand.net.nz/trac/libtrace/browser/Intel%20DPDK%20Patches/
hardware_timestamp.patch?rev=ce7153dbc6a13c18bf8033af08c1249527754168), but
it only works in e1000 and igb NICs. I want to capture
Hi Jan,
On 05/29/2015 12:34 PM, Jan Blunck wrote:
> In rte_log_dump_history() the log_history list is reinitialized without
> resetting the log_history_size. In the next call to rte_log_add_in_history()
> the log_history_size > RTE_LOG_HISTORY and the code unconditionally tries
> to remove the
Hi Helin,
+CC Neil
On 06/01/2015 09:33 AM, Helin Zhang wrote:
> In order to unify the packet type, the field of 'packet_type' in
> 'struct rte_mbuf' needs to be extended from 16 to 32 bits.
> Accordingly, some fields in 'struct rte_mbuf' are re-organized to
> support this change for Vector PMD.
Hi,
On 05/29/2015 11:04 PM, Dax Rawal wrote:
> Hi,
> How does one return (or destroy) ret_mempool that was created by
> rte_mempool_create() ?
Currently it's not possible but it seems it would be a nice improvement
to mempool library.
Sergio recently submitted a patch to delete memzones, it
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Maciej Gajdzica
> Sent: Friday, May 29, 2015 4:27 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 0/3] librte_cfgfile rework and extension
>
> From: Pawel Wodkowski
>
> This patchset provide extension
Never mind, had wrong version of one of the patches.
On Mon, Jun 1, 2015 at 7:11 AM, Stephen Hemminger
wrote:
> On Fri, 29 May 2015 16:45:25 +0800
> Cunming Liang wrote:
>
> > RTE_EAL_RX_INTR will be removed from v2.2. It's only used to avoid
> ABI(unannounced) broken in v2.1.
> > The usrs
On Fri, 29 May 2015 16:45:25 +0800
Cunming Liang wrote:
> RTE_EAL_RX_INTR will be removed from v2.2. It's only used to avoid
> ABI(unannounced) broken in v2.1.
> The usrs should make sure understand the impact before turning on the feature.
> There are two abi changes required in this interrupt
On Fri, 29 May 2015 17:43:08 +0200
Maciej Gajdzica wrote:
> +/**
> + * Find object of name *name* in *obj_array* which is constant size array of
> + * elements that have field *name*.
> + *
> + * @param obj_array
> + * Constant size array
> + * @param name
> + * name of object to find.
> + *
On Mon, 1 Jun 2015 16:48:01 +0800
"Liang, Cunming" wrote:
> Hi Stephen,
>
> On 5/29/2015 11:27 PM, Stephen Hemminger wrote:
> > On Fri, 29 May 2015 16:45:25 +0800
> > Cunming Liang wrote:
> >
> >> +#ifdef RTE_EAL_RX_INTR
> >> +extern int
> >> rte_eth_dev_rx_intr_ctl(uint8_t port_id, int
> -Original Message-
> From: Wei li [mailto:liw at dtdream.com]
> Sent: Monday, June 1, 2015 2:12 PM
> To: dev at dpdk.org
> Cc: Ouyang, Changchun; liw at dtdream.com
> Subject: [PATCH v2] lib_vhost:reset secure_len when rte_atomic16_cmpset
> failed
>
> when rte_atomic16_cmpset return 0
> -Original Message-
> From: Wei li [mailto:liw at dtdream.com]
> Sent: Monday, June 1, 2015 11:00 AM
> To: dev at dpdk.org
> Cc: Ouyang, Changchun
> Subject: [PATCH] lib_vhost:reset secure_len when rte_atomic16_cmpset
> failed
>
The one line change is ok, but need more description.
>
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Huawei Xie
> Sent: Wednesday, May 27, 2015 11:02 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] vhost: enable live migration
>
> When we migrate VM, without this feature, qemu will report error:
>
Prevent double initialization of the KNI subsytem.
Signed-off-by: Marc Sune
---
lib/librte_kni/rte_kni.c | 4
1 file changed, 4 insertions(+)
diff --git a/lib/librte_kni/rte_kni.c b/lib/librte_kni/rte_kni.c
index c5a0089..df0449f 100644
--- a/lib/librte_kni/rte_kni.c
+++
Signed-off-by: Wenfeng Liu
---
lib/librte_eal/linuxapp/kni/kni_misc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_eal/linuxapp/kni/kni_misc.c
b/lib/librte_eal/linuxapp/kni/kni_misc.c
index 1935d32..18fb677 100644
--- a/lib/librte_eal/linuxapp/kni/kni_misc.c
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jijiang Liu
> Sent: Thursday, May 28, 2015 9:36 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] config:enlarge the default value of
> RTE_MAX_QUEUES_PER_PORT to 1024
>
> The default value of
61 matches
Mail list logo